Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks
This work addresses the problem of inconsistent comparisons for researchers in multi-agent reinforcement learning, though it is incremental as it builds on existing frameworks.
The authors tackled the lack of standardized evaluation in multi-agent deep reinforcement learning by systematically benchmarking three classes of algorithms across diverse cooperative tasks, providing performance references and insights into their effectiveness.
Multi-agent deep reinforcement learning (MARL) suffers from a lack of commonly-used evaluation tasks and criteria, making comparisons between approaches difficult. In this work, we provide a systematic evaluation and comparison of three different classes of MARL algorithms (independent learning, centralised multi-agent policy gradient, value decomposition) in a diverse range of cooperative multi-agent learning tasks. Our experiments serve as a reference for the expected performance of algorithms across different learning tasks, and we provide insights regarding the effectiveness of different learning approaches. We open-source EPyMARL, which extends the PyMARL codebase to include additional algorithms and allow for flexible configuration of algorithm implementation details such as parameter sharing. Finally, we open-source two environments for multi-agent research which focus on coordination under sparse rewards.